fix(research): align evidence query limits

packages/agent-core/src/mastra/system-prompt.ts

@@ -233,7 +233,7 @@ Load the generate-media skill before creating or editing an image or generating
 
 const RESEARCH_MODULE = `## Research
 
-Gather sources with search_web / search_web_advanced / search_company / search_web_content, then use search_scrape or search_extract for source retrieval. For an explicit deep-research request, cited report, market analysis, due diligence, or comprehensive investigation of one topic, use research_deep with 3 queries for a concise/narrow report, 4 by default, and 5-6 only when the user explicitly asks for deeper coverage. Use research_fanout when the request compares many entities or independent angles. Call the selected research workflow once per user request; if it fails, explain the failure instead of immediately rerunning it. Those workflows produce the complete cited PDF deliverable automatically, so do not regenerate it with a document tool. After a research workflow succeeds, present its returned report Markdown as the response body without summarizing, restructuring, or appending hidden claim-map data; the PDF is rendered from that same Markdown. Treat search snippets as leads, not sources — open the real pages and cross-check. Cite as you go: attribute each claim to its source inline with the page title and its URL, and make sure every citation resolves. End a research answer with a short Sources list of the URLs you actually used.`;
+Gather sources with search_web / search_web_advanced / search_company / search_web_content, then use search_scrape or search_extract for source retrieval. For an explicit deep-research request, cited report, market analysis, due diligence, or comprehensive investigation of one topic, use research_deep with 3 queries for a concise/narrow report, 4 by default, and 5-6 only when the user explicitly asks for deeper coverage. A comparison of a few sources, standards, or recommendations within one topic still uses research_deep. Reserve research_fanout for four or more independent entities or genuinely separate angles, and pass entities as an array of separate short names. Call the selected research workflow once per user request; if it fails, explain the failure instead of immediately rerunning it. Those workflows produce the complete cited PDF deliverable automatically, so do not regenerate it with a document tool. After a research workflow succeeds, present its returned report Markdown as the response body without summarizing, restructuring, or appending hidden claim-map data; the PDF is rendered from that same Markdown. Treat search snippets as leads, not sources — open the real pages and cross-check. Cite as you go: attribute each claim to its source inline with the page title and its URL, and make sure every citation resolves. End a research answer with a short Sources list of the URLs you actually used.`;
 
 /** Compact all-domains pointer for an ambiguous general request — keeps the model aware without the full modules. */
 const GENERALIST_MODULE = `## Choosing your approach

packages/agent-core/src/mastra/tool-defs/research-tools.ts

@@ -279,7 +279,7 @@ export const mastraDeepResearch = createTool({
 export const mastraResearchFanout = createTool({
   id: "research_fanout",
   description:
-    "Run the Deep Research fan-out workflow across multiple entities or angles. It returns a cited comparison report and saves the complete report as a PDF deliverable in the project.",
+    "Run Deep Research across four or more independent entities or genuinely separate angles. Pass entities as an array of separate short names. For comparisons of a few sources or standards within one topic, use research_deep. The workflow returns a cited comparison report and saves the complete report as a PDF deliverable in the project.",
   inputSchema: DeepResearchFanoutInputSchema,
   outputSchema: ResearchReportArtifactSchema,
   execute: async (input, context) => {

packages/agent-core/src/mastra/workflows/research-schemas.ts

@@ -41,7 +41,7 @@ export const ResearchReportSchema = z.strictObject({
 });
 
 export const ResearchQuerySchema = z.strictObject({
-  query: z.string().trim().min(1).max(2_000),
+  query: z.string().trim().min(1).max(1_000),
 });
 
 export const DeepResearchInputSchema = z.strictObject({
@@ -65,7 +65,14 @@ export const DeepResearchInputSchema = z.strictObject({
 });
 
 export const DeepResearchFanoutInputSchema = z.strictObject({
-  entities: z.array(z.string().trim().min(1).max(200)).min(1).max(12).optional(),
+  entities: z
+    .array(z.string().trim().min(1).max(200))
+    .min(1)
+    .max(12)
+    .optional()
+    .describe(
+      "Optional array of separate short entity names; never combine entities into one string.",
+    ),
   goal: z.string().trim().min(1).max(2_000),
   maxQueries: z.number().int().min(1).max(12).default(10),
 });

packages/agent-core/src/mastra/workflows/research-support.ts

@@ -1,4 +1,4 @@
-const MAX_RESEARCH_QUERY_CHARACTERS = 2_000;
+const MAX_RESEARCH_QUERY_CHARACTERS = 1_000;
 
 export function buildDeepResearchQueries(
   topic: string,